Search papers, labs, and topics across Lattice.
This paper addresses the challenge of automatically quantifying natural language software performance requirements into mathematical functions. They propose IRAP, an interactive retrieval-augmented preference elicitation approach that leverages problem-specific knowledge to retrieve relevant information and guide interactions with stakeholders. Experiments on real-world datasets show IRAP outperforms state-of-the-art methods by up to 40x with minimal interaction rounds.
Quantifying vague software requirements doesn't have to be a guessing game: this method slashes the ambiguity with interactive preference elicitation, achieving 40x better results.
Since software performance requirements are documented in natural language, quantifying them into mathematical forms is essential for software engineering. Yet, the vagueness in performance requirements and uncertainty of human cognition have caused highly uncertain ambiguity in the interpretations, rendering their automated quantification an unaddressed and challenging problem. In this paper, we formalize the problem and propose IRAP, an approach that quantifies performance requirements into mathematical functions via interactive retrieval-augmented preference elicitation. IRAP differs from the others in that it explicitly derives from problem-specific knowledge to retrieve and reason the preferences, which also guides the progressive interaction with stakeholders, while reducing the cognitive overhead. Experiment results against 10 state-of-the-art methods on four real-world datasets demonstrate the superiority of IRAP on all cases with up to 40x improvements under as few as five rounds of interactions.
